© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 5-LLAMASCOPE-RES-131K
    11. 125457
    Prev
    Next
    INDEX
    Explanations

    numerical values related to constraints and violations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸ŃåѦ
    -0.07
    ÃĹ↵↵
    -0.07
     Overs
    -0.07
    adnÃŃ
    -0.07
     Roz
    -0.06
    _Syntax
    -0.06
    برد
    -0.06
    _scripts
    -0.06
    erif
    -0.06
    Ø·ÙĨ
    -0.06
    POSITIVE LOGITS
    aves
    0.07
    andas
    0.07
    reetings
    0.06
    ares
    0.06
    öh
    0.06
    ragon
    0.06
    utherford
    0.06
    iband
    0.06
    ked
    0.06
    anj
    0.06
    Activations Density 0.376%

    No Known Activations